← Back to community benchmarks
Qwen3-Coder-Next
Performance
4k
tokens
1,017
PP tok/s
48.7
TG tok/s
4026
TTFT (ms)
80.3
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 837.2 | 51.9 | 80.1 GB | view |
| 4k | 1,017 | 48.7 | 80.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.9 | 1.00× |
| 2× | 84.6 | 1.63× |
| 4× | 120.9 | 2.33× |